project-report

项目报表：大文件分布、模块代码量、大文件治理状态（gate/retained/baseline 新鲜度）一屏总览。只读。触发场景：用户说「项目报表」「项目整体情况」「大文件分布」「project report」。后续将扩展性能、测试健康、依赖等维度。

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an efficient, well-structured overview with good progressive disclosure and a sensible section sequence, but its actionability is limited because all executable commands live in an external file rather than the skill itself.

Suggestions

Inline at least the one or two core read-only commands (or a minimal copy-paste example) so the body is executable without first opening the external command file.

Confirm the referenced path `.claude/commands/project-report.md` is reliably present, since the body's actionability fully depends on that external file.

Add a brief validation note for the §5 placeholder section so it is clear how/when the reserved dimensions will be wired in.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview that assumes Claude's competence — it names the source-of-truth file and the section structure with no padding or restated concepts.	5 / 5
Actionability	It gives a specific pointer ('执行清单见 .claude/commands/project-report.md') and clear section structure, but the body itself contains no executable commands — all actionable detail is deferred to an external non-bundle path.	3 / 5
Workflow Clarity	A clear §1→§5 sequence is laid out with per-section independence and explicit failure handling ('单段失败标 N/A 不阻塞其余'), but no validate→fix→retry checkpoint is present (acceptable for a read-only skill).	4 / 5
Progressive Disclosure	A short, well-organized overview with a single clearly signaled one-level-deep reference to the command file; no bundle files to misorganize, so navigation is trivial.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to invoke it, with concrete trigger phrases. Minor room for broader synonym coverage in trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete report contents — '大文件分布', '模块代码量', '治理状态（gate/retained/baseline 新鲜度）', '只读' — giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	Clearly states what the skill produces (one-screen overview of distribution/code-volume/governance) and explicitly provides a '触发场景' clause with concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	Explicitly enumerates natural trigger phrases a user would say ('项目报表', '项目整体情况', '大文件分布', 'project report'), but lacks synonym variants and file-extension-style breadth needed for a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is specific — large-file governance reporting with gate/retained/baseline status — and the distinct trigger phrases minimize overlap with generic reporting skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhukunpenglinyutong/desktop-cc-gui
Path: .agents/skills/project-report/SKILL.md
Commit: 52259cf

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.